Gentoo Packages

Search

Package Information

Description:

Ollama is a tool for running large language models (LLMs) locally on your machine. It provides a simple interface to download, run, and manage models like Llama 3.2, Mistral, Gemma, and many others. This is a binary distribution package that installs pre-built binaries from the official Ollama releases. The binaries are provided under the MIT license and include GPU acceleration support for both NVIDIA (CUDA) and AMD (ROCm) graphics cards. Key features: - Easy model management with pull, push, and create commands - Built-in API server for programmatic access - GPU acceleration support (CUDA and ROCm) - Efficient memory management with automatic model loading/unloading - Support for multiple models and concurrent requests - Compatible with OpenAI API format Models are stored in /var/lib/ollama and can range from 2GB (3B parameters) to 40GB+ (70B parameters) in size. GPU acceleration significantly improves inference speed but requires compatible hardware. Security Note: This package installs pre-compiled binaries. Security hardening features (ASLR, PIE, stack protections) depend on upstream's build configuration. The service runs as a dedicated 'ollama' user with restricted permissions for defense in depth.

Homepage:

https://ollama.com/

License:

MIT

Versions

Metadata

Description

• Ollama is a tool for running large language models (LLMs) locally on your machine. It provides a simple interface to download, run, and manage models like Llama 3.2, Mistral, Gemma, and many others. This is a binary distribution package that installs pre-built binaries from the official Ollama releases. The binaries are provided under the MIT license and include GPU acceleration support for both NVIDIA (CUDA) and AMD (ROCm) graphics cards. Key features: - Easy model management with pull, push, and create commands - Built-in API server for programmatic access - GPU acceleration support (CUDA and ROCm) - Efficient memory management with automatic model loading/unloading - Support for multiple models and concurrent requests - Compatible with OpenAI API format Models are stored in /var/lib/ollama and can range from 2GB (3B parameters) to 40GB+ (70B parameters) in size. GPU acceleration significantly improves inference speed but requires compatible hardware. Security Note: This package installs pre-compiled binaries. Security hardening features (ASLR, PIE, stack protections) depend on upstream's build configuration. The service runs as a dedicated 'ollama' user with restricted permissions for defense in depth.

Maintainers

• Lucas C.S. (lucascs@proton.me) - Type: person

Upstream

• Bugs: https://github.com/ollama/ollama/issues
• Changelog: https://github.com/ollama/ollama/releases
• Remote IDs:
  • github: ollama/ollama

<pkgmetadata>
	<maintainer type="person">
		<email>lucascs@proton.me</email>
		<name>Lucas C.S.</name>
	</maintainer>
	<longdescription lang="en">
		Ollama is a tool for running large language models (LLMs) locally on your 
		machine. It provides a simple interface to download, run, and manage models 
		like Llama 3.2, Mistral, Gemma, and many others.

		This is a binary distribution package that installs pre-built binaries from 
		the official Ollama releases. The binaries are provided under the MIT license 
		and include GPU acceleration support for both NVIDIA (CUDA) and AMD (ROCm) 
		graphics cards.

		Key features:
		- Easy model management with pull, push, and create commands
		- Built-in API server for programmatic access
		- GPU acceleration support (CUDA and ROCm)
		- Efficient memory management with automatic model loading/unloading
		- Support for multiple models and concurrent requests
		- Compatible with OpenAI API format

		Models are stored in /var/lib/ollama and can range from 2GB (3B parameters) 
		to 40GB+ (70B parameters) in size. GPU acceleration significantly improves 
		inference speed but requires compatible hardware.

		Security Note: This package installs pre-compiled binaries. Security 
		hardening features (ASLR, PIE, stack protections) depend on upstream's 
		build configuration. The service runs as a dedicated 'ollama' user with 
		restricted permissions for defense in depth.
	</longdescription>
	<slots>
		<subslots>&#xA;&#x9;&#x9;&#x9;Package does not use subslots as it is a self-contained binary &#xA;&#x9;&#x9;&#x9;distribution. All dependencies are either bundled or runtime-only.&#xA;&#x9;&#x9;</subslots>
	</slots>
	<use>
		<flag name="cuda">
			Enable NVIDIA CUDA GPU acceleration support. Requires compatible NVIDIA 
			GPU (compute capability 6.0+, Pascal architecture or newer) and 
			nvidia-cuda-toolkit. Significantly improves inference performance for 
			large models.
		</flag>
		<flag name="rocm">
			Enable AMD ROCm GPU acceleration support. Requires compatible AMD GPU 
			(Radeon RX 6000 series or newer, or Radeon VII) and ROCm libraries. 
			May require HSA_OVERRIDE_GFX_VERSION environment variable for optimal 
			compatibility. This is experimental and not all GPU models are supported.
		</flag>
	</use>
	<upstream>
		<changelog>https://github.com/ollama/ollama/releases</changelog>
		<doc lang="en">https://github.com/ollama/ollama/tree/main/docs</doc>
		<bugs-to>https://github.com/ollama/ollama/issues</bugs-to>
		<remote-id type="github">ollama/ollama</remote-id>
	</upstream>
</pkgmetadata>

Lint Warnings

• [Warning] Ebuild 0.18.0 uses IUSE flag 'systemd' which is not documented in metadata.xml. Add the flag to metadata.xml <use> section.
• [Warning] Missing md5-cache for version 0.18.0. Run 'ebuild <ebuild_file> manifest' or 'egencache' to generate it.

USE Flags

Files

• ollama.conf
• ollama.confd
• ollama.initd
• ollama.service

Manifest